© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6181
    Prev
    Next
    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.29
     says
    0.27
     has
    0.27
    al
    0.26
     is
    0.26
     barges
    0.26
    ing
    0.25
    okane
    0.25
    fords
    0.25
     charters
    0.25
    POSITIVE LOGITS
    ไฟล์
    0.32
    ༢
    0.28
     ஆகியவை
    0.28
     तसेच
    0.26
     Tencent
    0.26
     мәкалә
    0.26
    ஃப்
    0.25
    等を
    0.25
    பிலோ
    0.25
     பூஜை
    0.25
    Activations Density 0.184%

    No Known Activations